In this study, the authors conducted a statistical investigation into the history of position-based racial segregation in the NFL. Specifically, they focused on the cornerback position, which they hypothesized would be occupied disproportionately by black players due to their historical stereotyping as more suitable for positions requiring extreme athletic ability. Using publicly available datasets on the demographics of NFL players over the past several decades, they confirmed their hypothesis that the cornerback position is skewed towards black players. They additionally discovered that, unlike in the quarterback position, this trend has shown no sign of decreasing over time.
The authors looked at the ability of Shewanella oneidensis to generate energy in a microbial fuel cell under varying conditions. They found that the S. Onedensis biofilm was able to produce energy in microgravity and that one of the biggest factors that limited energy production was a decrease in growth medium present.
The application of machine learning techniques has facilitated the automatic annotation of behavior in video sequences, offering a promising approach for ethological studies by reducing the manual effort required for annotating each video frame. Nevertheless, before solely relying on machine-generated annotations, it is essential to evaluate the accuracy of these annotations to ensure their reliability and applicability. While it is conventionally accepted that there cannot be a perfect annotation, the degree of error associated with machine-generated annotations should be commensurate with the error between different human annotators. We hypothesized that machine learning supervised with adequate human annotations would be able to accurately predict body parts from video sequences. Here, we conducted a comparative analysis of the quality of annotations generated by humans and machines for the body parts of sheep during treadmill walking. For human annotation, two annotators manually labeled six body parts of sheep in 300 frames. To generate machine annotations, we employed the state-of-the-art pose-estimating library, DeepLabCut, which was trained using the frames annotated by human annotators. As expected, the human annotations demonstrated high consistency between annotators. Notably, the machine learning algorithm also generated accurate predictions, with errors comparable to those between humans. We also observed that abnormal annotations with a high error could be revised by introducing Kalman Filtering, which interpolates the trajectory of body parts over the time series, enhancing robustness. Our results suggest that conventional transfer learning methods can generate behavior annotations as accurate as those made by humans, presenting great potential for further research.
In their paper, Kreiman et al. examined what it takes for an artificial neural network to be able to perform well on a new task without forgetting its previous knowledge. By comparing methods that stop task forgetting, they found that longer training times and maintenance of the most important connections in a particular task while training on a new one helped the neural network maintain its performance on both tasks. The authors hope that this proof-of-principle research will someday contribute to artificial intelligence that better mimics natural human intelligence.
In this study the authors looked at developing a more efficient particle collision classification method with the goal of being able to more efficiently analyze particle trajectories from large-scale particle collisions without loss of accuracy.
Alzheimer’s disease (AD) is a common disease affecting 6 million people in the U.S., but no cure exists. To create therapy for AD, it is critical to detect amyloid-β protein in the brain at the early stage of AD because the accumulation of amyloid-β over 20 years is believed to cause memory impairment. However, it is difficult to examine amyloid-β in patients’ brains. In this study, we hypothesized that we could accurately predict the presence of amyloid-β using EEG data and machine learning.
Lipases are a common class of enzymes that catalyze the breakdown of lipids. Here the authors characterize the the activity of pancreatic lipase in different organic solvents using a choloremetric assay, as well as using molecular dynamic simulations. They report that the activity of pancreatic lipase in 5% methanol is more than 25% higher than in water, despite enzyme stability being comparable in both solvents. This suggests that, for industrial applications, using pancreatic lipase in 5% methanol solution might increase yield, compared to just water.
In this study, the authors hypothesized that closed-circuit television images could be stored with improved resolution by using enhanced deep residual (EDSR) networks.
With healthy lung performance being critical to daily function and maintenance of physical health, the authors of this study explored the impact of airflow training from playing a wind instrument on respiratory system function. With careful quantification of peak expiratory flow of individuals who played the trumpet, the authors found no expiratory capacity difference between students who played the trumpet and students who did not play a wind instrument.